Optimize neural network models with Python and quantization techniques at STMicroelectronics’ in-person Toronto, Canada internship. Research accuracy and efficiency trade-offs.
As a Deep Learning Researcher Intern, you will implement low-bit approaches and investigate how quantization affects model performance. Your responsibilities include model analysis, mixed-precision research, and staying current with compression methods. You will also document experiments clearly for internal stakeholders.
Key Responsibilities:
- Implement low-bit quantization for deep learning models
- Investigate accuracy impacts and inference latency reductions
- Analyze model performance during quantization experiments
- Stay updated on compression and quantization research
- Prepare explicit technical documentation for internal stakeholders
Requirements:
- PhD or master’s degree in Computer Engineering or related field
- Proficiency in Python programming
- Experience using deep learning frameworks such as PyTorch
- Hands-on experience with quantization methods, including QAT and PTQ
- Familiarity with C++ is a plus
Use neural network knowledge, Python, and quantization experience to investigate efficient deep learning models at STMicroelectronics Toronto.
📌 Neural Network Optimization Research Intern (Toronto)
🏢 STMicroelectronics
📍 Toronto
Reply to this offer
Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.